© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136584
    Prev
    Next
    INDEX
    Explanations

    ETS GRE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    0.66
    }:
    0.51
    ר
    0.47
    :}
    0.46
    र
    0.46
    <0xA1>
    0.43
     rata
    0.43
    “
    0.42
    િમ
    0.42
    alada
    0.42
    POSITIVE LOGITS
     ನೇ
    0.54
     भाषाओं
    0.49
    ()
    0.48
    ровать
    0.47
     Bedarf
    0.47
    abling
    0.47
     أف
    0.46
     Utils
    0.46
     शक्यता
    0.46
     ዋና
    0.46
    Activations Density 0.000%

    No Known Activations